Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies, specifically focusing on the political Left

    oai_token-act-pair · gpt-3.5-turbo

    references to the political left

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.84
    andise
    -0.78
    è¦ļéĨĴ
    -0.74
     Allaah
    -0.71
    glomer
    -0.69
    ETA
    -0.68
     TOUR
    -0.66
     Frey
    -0.66
    CLASSIFIED
    -0.66
    riott
    -0.65
    POSITIVE LOGITS
    wing
    1.24
    overs
    1.20
     wing
    1.02
    ward
    0.98
    wich
    0.93
    hander
    0.92
     hemisphere
    0.87
     orthodoxy
    0.82
    isphere
    0.79
     flank
    0.79
    Act Density 0.023%

    No Known Activations